FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Paper • 2610.03675 • Published 27 days ago • 29
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 28 days ago • 299
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning Paper • 2610.02824 • Published 27 days ago • 33
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence Paper • 2609.34563 • Published Sep 28 • 227
AIM: Agentic Idea Management for Automated Research Paper • 2609.38445 • Published about 1 month ago • 53
Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces Paper • 2609.18587 • Published Sep 28 • 5
BIABench: Evaluating AI agents on real-world bioimage analysis tasks Paper • 2609.34274 • Published Sep 28 • 5
Aligning One-Step Generative Models with Reward-Weighted Transport Distillation Paper • 2609.30840 • Published Sep 25 • 3
Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD Paper • 2609.29142 • Published Sep 26 • 6
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends Paper • 2609.39661 • Published 29 days ago • 14
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution Paper • 2609.38349 • Published about 1 month ago • 25